Triple

T19717524
Position Surface form Disambiguated ID Type / Status
Subject UGTB E473517 entity
Predicate isHubFor P423 FINISHED
Object Georgian Airways NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Georgian Airways | Statement: [UGTB, isHubFor, Georgian Airways]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgian Airways
Context triple: [UGTB, isHubFor, Georgian Airways]
  • A. Georgian Airways chosen
    Georgian Airways is the flag carrier airline of Georgia, operating passenger flights primarily from its base in Tbilisi to destinations in Europe and the Middle East.
  • B. Air Georgian (former)
    Air Georgian was a Canadian regional airline that operated feeder and commuter flights on behalf of Air Canada under the Air Canada Express brand before ceasing operations.
  • C. Azerbaijan Airlines
    Azerbaijan Airlines is the national flag carrier airline of Azerbaijan, providing domestic and international passenger and cargo services primarily based out of Baku.
  • D. Hunnu Air
    Hunnu Air is a Mongolian airline that operates domestic and regional international flights, primarily serving as a key carrier based in Ulaanbaatar.
  • E. Bulgaria Air
    Bulgaria Air is the national flag carrier airline of Bulgaria, operating domestic and international flights across Europe and the Middle East.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6440ec9e881909b75c0ebefab827f completed April 20, 2026, 3:19 p.m.
Created at: April 10, 2026, 1:46 p.m.